FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4377090011> ?p ?o ?g. }

• W4377090011 endingPage "837" @default.
• W4377090011 startingPage "823" @default.
• W4377090011 abstract "The influence of non-Independent Identically Distribution (non-IID) data on Federated Learning (FL) has been a serious concern. Clustered Federated Learning (CFL) is an emerging approach for reducing the impact of non-IID data, which employs the client similarity calculated by relevant metrics for clustering. Unfortunately, the existing CFL methods only pursue a single accuracy improvement, but ignore the convergence rate. Additionlly, the designed client selection strategy will affect the clustering results. Finally, traditional semi-supervised learning changes the distribution of data on clients, resulting in higher local costs and undesirable performance. In this paper, we propose a novel CFL method named ASCFL, which selects clients to participate in training and can dynamically adjust the balance between accuracy and convergence speed with datasets consisting of labeled and unlabeled data. To deal with unlabeled data, the prediction labels strategy predicts labels by encoders. The client selection strategy is to improve accuracy and reduce overhead by selecting clients with higher losses participating in the current round. What is more, the similarity-based clustering strategy uses a new indicator to measure the similarity between clients. Experimental results show that ASCFL has certain advantages in model accuracy and convergence speed over the three state-of-the-art methods with two popular datasets." @default.
• W4377090011 created "2023-05-20" @default.
• W4377090011 creator A5005084423 @default.
• W4377090011 creator A5029081878 @default.
• W4377090011 creator A5034500976 @default.
• W4377090011 creator A5046734792 @default.
• W4377090011 creator A5084762460 @default.
• W4377090011 creator A5091483352 @default.
• W4377090011 date "2023-10-01" @default.
• W4377090011 modified "2023-10-05" @default.
• W4377090011 title "ASCFL: Accurate and Speedy Semi-Supervised Clustering Federated Learning" @default.
• W4377090011 cites W2025183033 @default.
• W4377090011 cites W2905156284 @default.
• W4377090011 cites W2954996726 @default.
• W4377090011 cites W2967912576 @default.
• W4377090011 cites W2968508074 @default.
• W4377090011 cites W2989289980 @default.
• W4377090011 cites W3011892127 @default.
• W4377090011 cites W3027859434 @default.
• W4377090011 cites W3047304572 @default.
• W4377090011 cites W3080934299 @default.
• W4377090011 cites W3089714714 @default.
• W4377090011 cites W3089956757 @default.
• W4377090011 cites W3091635927 @default.
• W4377090011 cites W3092144916 @default.
• W4377090011 cites W3093755649 @default.
• W4377090011 cites W3105122387 @default.
• W4377090011 cites W3110088280 @default.
• W4377090011 cites W3115750078 @default.
• W4377090011 cites W3119097278 @default.
• W4377090011 cites W3123131059 @default.
• W4377090011 cites W3126441351 @default.
• W4377090011 cites W3161652179 @default.
• W4377090011 cites W3163004056 @default.
• W4377090011 cites W3174370604 @default.
• W4377090011 cites W3193610988 @default.
• W4377090011 cites W3204597713 @default.
• W4377090011 cites W3211781253 @default.
• W4377090011 cites W4200274560 @default.
• W4377090011 cites W4206123967 @default.
• W4377090011 cites W4210331355 @default.
• W4377090011 cites W4211226080 @default.
• W4377090011 cites W4214626077 @default.
• W4377090011 cites W4225482284 @default.
• W4377090011 cites W4226484282 @default.
• W4377090011 cites W4281660018 @default.
• W4377090011 cites W4281755684 @default.
• W4377090011 cites W4306178637 @default.
• W4377090011 cites W4312429505 @default.
• W4377090011 cites W4312462223 @default.
• W4377090011 doi "https://doi.org/10.26599/tst.2022.9010057" @default.
• W4377090011 hasPublicationYear "2023" @default.
• W4377090011 type Work @default.
• W4377090011 citedByCount "2" @default.
• W4377090011 crossrefType "journal-article" @default.
• W4377090011 hasAuthorship W4377090011A5005084423 @default.
• W4377090011 hasAuthorship W4377090011A5029081878 @default.
• W4377090011 hasAuthorship W4377090011A5034500976 @default.
• W4377090011 hasAuthorship W4377090011A5046734792 @default.
• W4377090011 hasAuthorship W4377090011A5084762460 @default.
• W4377090011 hasAuthorship W4377090011A5091483352 @default.
• W4377090011 hasBestOaLocation W43770900111 @default.
• W4377090011 hasConcept C103278499 @default.
• W4377090011 hasConcept C111919701 @default.
• W4377090011 hasConcept C115961682 @default.
• W4377090011 hasConcept C119857082 @default.
• W4377090011 hasConcept C124101348 @default.
• W4377090011 hasConcept C154945302 @default.
• W4377090011 hasConcept C162324750 @default.
• W4377090011 hasConcept C2777303404 @default.
• W4377090011 hasConcept C2779960059 @default.
• W4377090011 hasConcept C41008148 @default.
• W4377090011 hasConcept C50522688 @default.
• W4377090011 hasConcept C73555534 @default.
• W4377090011 hasConcept C81917197 @default.
• W4377090011 hasConceptScore W4377090011C103278499 @default.
• W4377090011 hasConceptScore W4377090011C111919701 @default.
• W4377090011 hasConceptScore W4377090011C115961682 @default.
• W4377090011 hasConceptScore W4377090011C119857082 @default.
• W4377090011 hasConceptScore W4377090011C124101348 @default.
• W4377090011 hasConceptScore W4377090011C154945302 @default.
• W4377090011 hasConceptScore W4377090011C162324750 @default.
• W4377090011 hasConceptScore W4377090011C2777303404 @default.
• W4377090011 hasConceptScore W4377090011C2779960059 @default.
• W4377090011 hasConceptScore W4377090011C41008148 @default.
• W4377090011 hasConceptScore W4377090011C50522688 @default.
• W4377090011 hasConceptScore W4377090011C73555534 @default.
• W4377090011 hasConceptScore W4377090011C81917197 @default.
• W4377090011 hasFunder F4320321001 @default.
• W4377090011 hasFunder F4320335777 @default.
• W4377090011 hasIssue "5" @default.
• W4377090011 hasLocation W43770900111 @default.
• W4377090011 hasOpenAccess W4377090011 @default.
• W4377090011 hasPrimaryLocation W43770900111 @default.
• W4377090011 hasRelatedWork W2028024605 @default.
• W4377090011 hasRelatedWork W2762277149 @default.
• W4377090011 hasRelatedWork W2961085424 @default.
• W4377090011 hasRelatedWork W3046775127 @default.

• next